How to access Hive table from Spark in MapR sandbox

I was trying to figure out how to query a hive table from spark in MapR 5.1 sandbox . So i started spark-shell and tried to query the sample_08 table and i got error saying no such table exists

scala> val sample08 = sqlContext.sql("select * from sample_08")
org.apache.spark.sql.AnalysisException: no such table sample_08; line 1 pos 14
 at org.apache.spark.sql.catalyst.analysis.package$AnalysisErrorAt.failAnalysis(package.scala:42)
 at org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveRelations$.getTable(Analyzer.scala:260)
 at org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveRelations$$anonfun$apply$7.applyOrElse(Analyzer.scala:268)
 at org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveRelations$$anonfun$apply$7.applyOrElse(Analyzer.scala:264)
 at org.apache.spark.sql.catalyst.plans.logical.LogicalPlan$$anonfun$resolveOperators$1.apply(LogicalPlan.scala:57)
 at org.apache.spark.sql.catalyst.plans.logical.LogicalPlan$$anonfun$resolveOperators$1.apply(LogicalPlan.scala:57)
 at org.apache.spark.sql.catalyst.trees.CurrentOrigin$.withOrigin(TreeNode.scala:51)
 at org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.resolveOperators(LogicalPlan.scala:56)
 at org.apache.spark.sql.catalyst.plans.logical.LogicalPlan$$anonfun$1.apply(LogicalPlan.scala:54)
 at org.apache.spark.sql.catalyst.plans.logical.LogicalPlan$$anonfun$1.apply(LogicalPlan.scala:54)
 at org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$4.apply(TreeNode.scala:249)
 at scala.collection.Iterator$$anon$11.next(Iterator.scala:328)
 at scala.collection.Iterator$class.foreach(Iterator.scala:727)
 at scala.collection.AbstractIterator.foreach(Iterator.scala:1157)
 at scala.collection.generic.Growable$class.$plus$plus$eq(Growable.scala:48)
 at scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:103)
 at scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:47)
 at scala.collection.TraversableOnce$class.to(TraversableOnce.scala:273)
 at scala.collection.AbstractIterator.to(Iterator.scala:1157)
 at scala.collection.TraversableOnce$class.toBuffer(TraversableOnce.scala:265)
 at scala.collection.AbstractIterator.toBuffer(Iterator.scala:1157)
 at scala.collection.TraversableOnce$class.toArray(TraversableOnce.scala:252)
 at scala.collection.AbstractIterator.toArray(Iterator.scala:1157)
 at org.apache.spark.sql.catalyst.trees.TreeNode.transformChildren(TreeNode.scala:279)
 at org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.resolveOperators(LogicalPlan.scala:54)
 at org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveRelations$.apply(Analyzer.scala:264)
 at org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveRelations$.apply(Analyzer.scala:254)
 at org.apache.spark.sql.catalyst.rules.RuleExecutor$$anonfun$execute$1$$anonfun$apply$1.apply(RuleExecutor.scala:83)
 at org.apache.spark.sql.catalyst.rules.RuleExecutor$$anonfun$execute$1$$anonfun$apply$1.apply(RuleExecutor.scala:80)
 at scala.collection.LinearSeqOptimized$class.foldLeft(LinearSeqOptimized.scala:111)
 at scala.collection.immutable.List.foldLeft(List.scala:84)
 at org.apache.spark.sql.catalyst.rules.RuleExecutor$$anonfun$execute$1.apply(RuleExecutor.scala:80)
 at org.apache.spark.sql.catalyst.rules.RuleExecutor$$anonfun$execute$1.apply(RuleExecutor.scala:72)
 at scala.collection.immutable.List.foreach(List.scala:318)
 at org.apache.spark.sql.catalyst.rules.RuleExecutor.execute(RuleExecutor.scala:72)
 at org.apache.spark.sql.SQLContext$QueryExecution.analyzed$lzycompute(SQLContext.scala:932)
 at org.apache.spark.sql.SQLContext$QueryExecution.analyzed(SQLContext.scala:932)
 at org.apache.spark.sql.SQLContext$QueryExecution.assertAnalyzed(SQLContext.scala:930)
 at org.apache.spark.sql.DataFrame.(DataFrame.scala:132)
 at org.apache.spark.sql.DataFrame$.apply(DataFrame.scala:51)
 at org.apache.spark.sql.SQLContext.sql(SQLContext.scala:741)
 at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.(:19)
 at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.(:24)
 at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC.(:26)
 at $iwC$$iwC$$iwC$$iwC$$iwC.(:28)
 at $iwC$$iwC$$iwC$$iwC.(:30)
 at $iwC$$iwC$$iwC.(:32)
 at $iwC$$iwC.(:34)
 at $iwC.(:36)
 at (:38)
 at .(:42)
 at .()
 at .(:7)
 at .()
 at $print()
 at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
 at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)
 at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
 at java.lang.reflect.Method.invoke(Method.java:606)
 at org.apache.spark.repl.SparkIMain$ReadEvalPrint.call(SparkIMain.scala:1065)
 at org.apache.spark.repl.SparkIMain$Request.loadAndRun(SparkIMain.scala:1340)
 at org.apache.spark.repl.SparkIMain.loadAndRunReq$1(SparkIMain.scala:840)
 at org.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:871)
 at org.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:819)
 at org.apache.spark.repl.SparkILoop.reallyInterpret$1(SparkILoop.scala:857)
 at org.apache.spark.repl.SparkILoop.interpretStartingWith(SparkILoop.scala:902)
 at org.apache.spark.repl.SparkILoop.command(SparkILoop.scala:814)
 at org.apache.spark.repl.SparkILoop.processLine$1(SparkILoop.scala:657)
 at org.apache.spark.repl.SparkILoop.innerLoop$1(SparkILoop.scala:665)
 at org.apache.spark.repl.SparkILoop.org$apache$spark$repl$SparkILoop$$loop(SparkILoop.scala:670)
 at org.apache.spark.repl.SparkILoop$$anonfun$org$apache$spark$repl$SparkILoop$$process$1.apply$mcZ$sp(SparkILoop.scala:997)
 at org.apache.spark.repl.SparkILoop$$anonfun$org$apache$spark$repl$SparkILoop$$process$1.apply(SparkILoop.scala:945)
 at org.apache.spark.repl.SparkILoop$$anonfun$org$apache$spark$repl$SparkILoop$$process$1.apply(SparkILoop.scala:945)
 at scala.tools.nsc.util.ScalaClassLoader$.savingContextLoader(ScalaClassLoader.scala:135)
 at org.apache.spark.repl.SparkILoop.org$apache$spark$repl$SparkILoop$$process(SparkILoop.scala:945)
 at org.apache.spark.repl.SparkILoop.process(SparkILoop.scala:1059)
 at org.apache.spark.repl.Main$.main(Main.scala:31)
 at org.apache.spark.repl.Main.main(Main.scala)
 at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
 at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)
 at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
 at java.lang.reflect.Method.invoke(Method.java:606)
 at org.apache.spark.deploy.SparkSubmit$.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:674)
 at org.apache.spark.deploy.SparkSubmit$.doRunMain$1(SparkSubmit.scala:180)
 at org.apache.spark.deploy.SparkSubmit$.submit(SparkSubmit.scala:205)
 at org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:120)
 at org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
When i checked the <SPARK_HOME>/conf directory i noticed that hive-site.xml was missing so i searched for hive-site.xml on the cluster i found 2 hive-site.xml but the /opt/mapr/hive/hive-1.2/conf/hive-site.xml had hive.metastore.uris property pointing to thrift://localhost:9083, so i copied it in the hive-site.xml and restarted the shell. When i execute the same query i can see the results.

scala> val sample08 = sqlContext.sql("select * from sample_08")
sample08: org.apache.spark.sql.DataFrame = [code: string, description: string, total_emp: int, salary: int]

2 comments:

  1. I like your post very much. It is nice useful for my research. I wish for you to share more info about this. Keep blogging Apache Kafka Training in Electronic City

    ReplyDelete
  2. Thank you for sharing such attractive and enjoyable information, I am very thankful to you for providing nice information. UAE VPS Server nice blog

    ReplyDelete